Litellm Minor Fixes & Improvements (10/03/2024) (#6049)

* fix(proxy_server.py): remove spendlog fixes from proxy startup logic

Moves  https://github.com/BerriAI/litellm/pull/4794 to `/db_scripts` and cleans up some caching-related debug info (easier to trace debug logs)

* fix(langfuse_endpoints.py): Fixes https://github.com/BerriAI/litellm/issues/6041

* fix(azure.py): fix health checks for azure audio transcription models

Fixes https://github.com/BerriAI/litellm/issues/5999

* Feat: Add Literal AI Integration (#5653)

* feat: add Literal AI integration

* update readme

* Update README.md

* fix: address comments

* fix: remove literalai sdk

* fix: use HTTPHandler

* chore: add test

* fix: add asyncio lock

* fix(literal_ai.py): fix linting errors

* fix(literal_ai.py): fix linting errors

* refactor: cleanup

---------

Co-authored-by: Willy Douhard <willy.douhard@gmail.com>

litellm/proxy/vertex_ai_endpoints/langfuse_endpoints.py

@@ -140,6 +140,7 @@ async def langfuse_proxy_route(
         request,
         fastapi_response,
         user_api_key_dict,
+        query_params=dict(request.query_params),  # type: ignore
     )
 
     return received_value